Computational Photography Under Low-Light Conditions

Abstract

This document describes techniques and apparatuses for computational photography under low-light conditions for an image-capture device on a mobile computing device. In aspects, described are techniques and apparatuses for an image-capture device to utilize sensor data in determining whether to enable flash photography or capture multiple images of the scene without use of a flash under low-light conditions. In other aspects, an image-capture device may utilize device data in determining whether to enable flash photography or capture multiple images of the scene without use of a flash under low-light conditions. The disclosed techniques and apparatuses may provide improved computational photography under low-light conditions for an image-capture device on a mobile computing device.

1 . A method comprising:
 receiving, at a mobile computing device and during a low-light condition for a scene, sensor data concerning ambient conditions of the scene;   selecting to capture, based on the received sensor data concerning the ambient conditions of the scene and using one or more image-capture devices of the mobile computing device, multiple images of the scene without use of a flash;   responsive to capturing the multiple images of the scene without use of the flash, generating a post-computational image using the multiple images of the scene; and   providing the post-computational image.   
     
     
         2 . The method as claimed in  claim 1 , wherein the method further comprises receiving device data concerning power consumption on the mobile computing device, and wherein selecting to capture multiple images of the scene without use of the flash is further based on the power consumption. 
     
     
         3 . The method as claimed in  claim 2 , wherein the power consumption includes power to:
 generate the flash for the one or more image-capture devices;   adjust a shutter of the one or more image-capture devices;   adjust a lens of the one or more image-capture devices; or   generate the post-computational image.   
     
     
         4 . The method as claimed in  claim 1 , wherein selecting to capture the multiple images of the scene without use of the flash performs machine learning, the machine learning based on the sensor data concerning ambient conditions of the scene, the low-light condition for the scene, and a machine-learned expectation of an image quality of the post-computational image or an image quality captured using the flash. 
     
     
         5 . The method as claimed in  claim 1 , wherein selecting to capture the multiple images of the scene without use of the flash performs machine learning, the machine learning utilizing a machine-learning model created using training data comprising sensor data concerning ambient conditions, low-light conditions, and a human-selected preference for a non-flash captured image or a flash-captured image. 
     
     
         6 . The method as claimed in  claim 5 , wherein the machine-learning model comprises a convoluted neural network, the convoluted neural network having a first convolutional layer comprising geometric shape classifications identified by pixel values. 
     
     
         7 . The method as claimed in  claim 6 , wherein the convoluted neural network comprises a second convolutional layer, the second convolutional layer comprising scene elements determined based on the geometric shapes classifications within the first convolutional layer. 
     
     
         8 . The method as claimed in  claim 1 , wherein the sensor data includes brightness data and the sensor data is received, at least in part, from a spectral sensor integrated with the mobile computing device, and wherein selecting to capture multiple images of the scene without use of the flash is based on the brightness data. 
     
     
         9 . The method as claimed in  claim 1 , wherein the sensor data includes motion-detection data and the sensor data is received, at least in part, from a spectral sensor in a pre-flash setting, and wherein selecting to capture multiple images of the scene without use of the flash is based on the motion-detection data. 
     
     
         10 . The method as claimed in  claim 1 , wherein the sensor data includes scene-type data and the sensor data is received, at least in part, from a spectral sensor integrated with the mobile computing device and wherein selecting to capture multiple images of the scene without use of the flash is based on the scene-type data. 
     
     
         11 . The method as claimed in  claim 1 , wherein the sensor data includes distance data and selecting to capture multiple images of the scene without use of the flash is based on the distance data. 
     
     
         12 . The method as claimed in  claim 1 , wherein the sensor data includes object reflectivity data and selecting to capture multiple images of the scene without use of the flash is based on the object reflectivity data. 
     
     
         13 . The method as claimed in  claim 1 , wherein the sensor data includes non-imaging data collected from an accelerometer, the data collected from the accelerometer indicating whether the image-capture device maintains stability necessary for selecting to capture multiple images of the scene without use of a flash. 
     
     
         14 . The method as claimed in  claim 1 , wherein selecting to capture multiple images of the scene without use of the flash is based on a weighted-sum equation, the weighted-sum equation including:
 an assigned weighted value to two or more device data, the two or more device data including power consumption to:   generate a flash for the one or more image-capture devices;   adjust a shutter of the one or more image-capture devices;   adjust a lens of the one or more image-capture devices; or   generate a post-computational image;   wherein the weighted values generate a sum, and wherein the selecting to capture multiple images of the scene without use of a flash is based on the sum exceeding a threshold.   
     
     
         15 . A mobile computing device comprising:
 a processor;   one or more sensors, image sensors, or flash generators; and   a computer-readable storage medium having stored thereon instructions that, responsive to execution by the processor, cause the processor to:   receive, during a low-light condition for a scene, sensor data concerning ambient conditions of the scene;   select to capture, based on the received sensor data concerning the ambient conditions of the scene and using one or more image-capture devices of the mobile computing device, multiple images of the scene without use of a flash;   responsive to capturing the multiple images of the scene without use of the flash, generate a post-computational image using the multiple images of the scene; and   provide the post-computational image.